aboutsummaryrefslogtreecommitdiff
path: root/mm/cleancache.c
diff options
context:
space:
mode:
authorDan Magenheimer <dan.magenheimer@oracle.com>2011-05-26 10:01:36 -0600
committerDan Magenheimer <dan.magenheimer@oracle.com>2011-05-26 10:01:36 -0600
commit077b1f83a69d94f2918630a882d74939baca0bce (patch)
tree96c47594b48df7dd588e3d8827f0ac151c350bc0 /mm/cleancache.c
parent9fdfdcf17151e8326c4d18cc133abc6e58f47568 (diff)
downloadlinux-077b1f83a69d94f2918630a882d74939baca0bce.tar.gz
mm: cleancache core ops functions and config
This third patch of eight in this cleancache series provides the core code for cleancache that interfaces between the hooks in VFS and individual filesystems and a cleancache backend. It also includes build and config patches. Two new files are added: mm/cleancache.c and include/linux/cleancache.h. Note that CONFIG_CLEANCACHE can default to on; in systems that do not provide a cleancache backend, all hooks devolve to a simple check of a global enable flag, so performance impact should be negligible but can be reduced to zero impact if config'ed off. However for this first commit, it defaults to off. Details and a FAQ can be found in Documentation/vm/cleancache.txt Credits: Cleancache_ops design derived from Jeremy Fitzhardinge design for tmem [v8: dan.magenheimer@oracle.com: fix exportfs call affecting btrfs] [v8: akpm@linux-foundation.org: use static inline function, not macro] [v7: dan.magenheimer@oracle.com: cleanup sysfs and remove cleancache prefix] [v6: JBeulich@novell.com: robustly handle buggy fs encode_fh actor definition] [v5: jeremy@goop.org: clean up global usage and static var names] [v5: jeremy@goop.org: simplify init hook and any future fs init changes] [v5: hch@infradead.org: cleaner non-global interface for ops registration] [v4: adilger@sun.com: interface must support exportfs FS's] [v4: hch@infradead.org: interface must support 64-bit FS on 32-bit kernel] [v3: akpm@linux-foundation.org: use one ops struct to avoid pointer hops] [v3: akpm@linux-foundation.org: document and ensure PageLocked reqts are met] [v3: ngupta@vflare.org: fix success/fail codes, change funcs to void] [v2: viro@ZenIV.linux.org.uk: use sane types] Signed-off-by: Dan Magenheimer <dan.magenheimer@oracle.com> Reviewed-by: Jeremy Fitzhardinge <jeremy@goop.org> Reviewed-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> Acked-by: Al Viro <viro@ZenIV.linux.org.uk> Acked-by: Andrew Morton <akpm@linux-foundation.org> Acked-by: Nitin Gupta <ngupta@vflare.org> Acked-by: Minchan Kim <minchan.kim@gmail.com> Acked-by: Andreas Dilger <adilger@sun.com> Acked-by: Jan Beulich <JBeulich@novell.com> Cc: Matthew Wilcox <matthew@wil.cx> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Mel Gorman <mel@csn.ul.ie> Cc: Rik Van Riel <riel@redhat.com> Cc: Chris Mason <chris.mason@oracle.com> Cc: Ted Ts'o <tytso@mit.edu> Cc: Mark Fasheh <mfasheh@suse.com> Cc: Joel Becker <joel.becker@oracle.com>
Diffstat (limited to 'mm/cleancache.c')
-rw-r--r--mm/cleancache.c244
1 files changed, 244 insertions, 0 deletions
diff --git a/mm/cleancache.c b/mm/cleancache.c
new file mode 100644
index 00000000000..bcaae4c2a77
--- /dev/null
+++ b/mm/cleancache.c
@@ -0,0 +1,244 @@
+/*
+ * Cleancache frontend
+ *
+ * This code provides the generic "frontend" layer to call a matching
+ * "backend" driver implementation of cleancache. See
+ * Documentation/vm/cleancache.txt for more information.
+ *
+ * Copyright (C) 2009-2010 Oracle Corp. All rights reserved.
+ * Author: Dan Magenheimer
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ */
+
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/exportfs.h>
+#include <linux/mm.h>
+#include <linux/cleancache.h>
+
+/*
+ * This global enablement flag may be read thousands of times per second
+ * by cleancache_get/put/flush even on systems where cleancache_ops
+ * is not claimed (e.g. cleancache is config'ed on but remains
+ * disabled), so is preferred to the slower alternative: a function
+ * call that checks a non-global.
+ */
+int cleancache_enabled;
+EXPORT_SYMBOL(cleancache_enabled);
+
+/*
+ * cleancache_ops is set by cleancache_ops_register to contain the pointers
+ * to the cleancache "backend" implementation functions.
+ */
+static struct cleancache_ops cleancache_ops;
+
+/* useful stats available in /sys/kernel/mm/cleancache */
+static unsigned long cleancache_succ_gets;
+static unsigned long cleancache_failed_gets;
+static unsigned long cleancache_puts;
+static unsigned long cleancache_flushes;
+
+/*
+ * register operations for cleancache, returning previous thus allowing
+ * detection of multiple backends and possible nesting
+ */
+struct cleancache_ops cleancache_register_ops(struct cleancache_ops *ops)
+{
+ struct cleancache_ops old = cleancache_ops;
+
+ cleancache_ops = *ops;
+ cleancache_enabled = 1;
+ return old;
+}
+EXPORT_SYMBOL(cleancache_register_ops);
+
+/* Called by a cleancache-enabled filesystem at time of mount */
+void __cleancache_init_fs(struct super_block *sb)
+{
+ sb->cleancache_poolid = (*cleancache_ops.init_fs)(PAGE_SIZE);
+}
+EXPORT_SYMBOL(__cleancache_init_fs);
+
+/* Called by a cleancache-enabled clustered filesystem at time of mount */
+void __cleancache_init_shared_fs(char *uuid, struct super_block *sb)
+{
+ sb->cleancache_poolid =
+ (*cleancache_ops.init_shared_fs)(uuid, PAGE_SIZE);
+}
+EXPORT_SYMBOL(__cleancache_init_shared_fs);
+
+/*
+ * If the filesystem uses exportable filehandles, use the filehandle as
+ * the key, else use the inode number.
+ */
+static int cleancache_get_key(struct inode *inode,
+ struct cleancache_filekey *key)
+{
+ int (*fhfn)(struct dentry *, __u32 *fh, int *, int);
+ int len = 0, maxlen = CLEANCACHE_KEY_MAX;
+ struct super_block *sb = inode->i_sb;
+
+ key->u.ino = inode->i_ino;
+ if (sb->s_export_op != NULL) {
+ fhfn = sb->s_export_op->encode_fh;
+ if (fhfn) {
+ struct dentry d;
+ d.d_inode = inode;
+ len = (*fhfn)(&d, &key->u.fh[0], &maxlen, 0);
+ if (len <= 0 || len == 255)
+ return -1;
+ if (maxlen > CLEANCACHE_KEY_MAX)
+ return -1;
+ }
+ }
+ return 0;
+}
+
+/*
+ * "Get" data from cleancache associated with the poolid/inode/index
+ * that were specified when the data was put to cleanache and, if
+ * successful, use it to fill the specified page with data and return 0.
+ * The pageframe is unchanged and returns -1 if the get fails.
+ * Page must be locked by caller.
+ */
+int __cleancache_get_page(struct page *page)
+{
+ int ret = -1;
+ int pool_id;
+ struct cleancache_filekey key = { .u.key = { 0 } };
+
+ VM_BUG_ON(!PageLocked(page));
+ pool_id = page->mapping->host->i_sb->cleancache_poolid;
+ if (pool_id < 0)
+ goto out;
+
+ if (cleancache_get_key(page->mapping->host, &key) < 0)
+ goto out;
+
+ ret = (*cleancache_ops.get_page)(pool_id, key, page->index, page);
+ if (ret == 0)
+ cleancache_succ_gets++;
+ else
+ cleancache_failed_gets++;
+out:
+ return ret;
+}
+EXPORT_SYMBOL(__cleancache_get_page);
+
+/*
+ * "Put" data from a page to cleancache and associate it with the
+ * (previously-obtained per-filesystem) poolid and the page's,
+ * inode and page index. Page must be locked. Note that a put_page
+ * always "succeeds", though a subsequent get_page may succeed or fail.
+ */
+void __cleancache_put_page(struct page *page)
+{
+ int pool_id;
+ struct cleancache_filekey key = { .u.key = { 0 } };
+
+ VM_BUG_ON(!PageLocked(page));
+ pool_id = page->mapping->host->i_sb->cleancache_poolid;
+ if (pool_id >= 0 &&
+ cleancache_get_key(page->mapping->host, &key) >= 0) {
+ (*cleancache_ops.put_page)(pool_id, key, page->index, page);
+ cleancache_puts++;
+ }
+}
+EXPORT_SYMBOL(__cleancache_put_page);
+
+/*
+ * Flush any data from cleancache associated with the poolid and the
+ * page's inode and page index so that a subsequent "get" will fail.
+ */
+void __cleancache_flush_page(struct address_space *mapping, struct page *page)
+{
+ /* careful... page->mapping is NULL sometimes when this is called */
+ int pool_id = mapping->host->i_sb->cleancache_poolid;
+ struct cleancache_filekey key = { .u.key = { 0 } };
+
+ if (pool_id >= 0) {
+ VM_BUG_ON(!PageLocked(page));
+ if (cleancache_get_key(mapping->host, &key) >= 0) {
+ (*cleancache_ops.flush_page)(pool_id, key, page->index);
+ cleancache_flushes++;
+ }
+ }
+}
+EXPORT_SYMBOL(__cleancache_flush_page);
+
+/*
+ * Flush all data from cleancache associated with the poolid and the
+ * mappings's inode so that all subsequent gets to this poolid/inode
+ * will fail.
+ */
+void __cleancache_flush_inode(struct address_space *mapping)
+{
+ int pool_id = mapping->host->i_sb->cleancache_poolid;
+ struct cleancache_filekey key = { .u.key = { 0 } };
+
+ if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0)
+ (*cleancache_ops.flush_inode)(pool_id, key);
+}
+EXPORT_SYMBOL(__cleancache_flush_inode);
+
+/*
+ * Called by any cleancache-enabled filesystem at time of unmount;
+ * note that pool_id is surrendered and may be reutrned by a subsequent
+ * cleancache_init_fs or cleancache_init_shared_fs
+ */
+void __cleancache_flush_fs(struct super_block *sb)
+{
+ if (sb->cleancache_poolid >= 0) {
+ int old_poolid = sb->cleancache_poolid;
+ sb->cleancache_poolid = -1;
+ (*cleancache_ops.flush_fs)(old_poolid);
+ }
+}
+EXPORT_SYMBOL(__cleancache_flush_fs);
+
+#ifdef CONFIG_SYSFS
+
+/* see Documentation/ABI/xxx/sysfs-kernel-mm-cleancache */
+
+#define CLEANCACHE_SYSFS_RO(_name) \
+ static ssize_t cleancache_##_name##_show(struct kobject *kobj, \
+ struct kobj_attribute *attr, char *buf) \
+ { \
+ return sprintf(buf, "%lu\n", cleancache_##_name); \
+ } \
+ static struct kobj_attribute cleancache_##_name##_attr = { \
+ .attr = { .name = __stringify(_name), .mode = 0444 }, \
+ .show = cleancache_##_name##_show, \
+ }
+
+CLEANCACHE_SYSFS_RO(succ_gets);
+CLEANCACHE_SYSFS_RO(failed_gets);
+CLEANCACHE_SYSFS_RO(puts);
+CLEANCACHE_SYSFS_RO(flushes);
+
+static struct attribute *cleancache_attrs[] = {
+ &cleancache_succ_gets_attr.attr,
+ &cleancache_failed_gets_attr.attr,
+ &cleancache_puts_attr.attr,
+ &cleancache_flushes_attr.attr,
+ NULL,
+};
+
+static struct attribute_group cleancache_attr_group = {
+ .attrs = cleancache_attrs,
+ .name = "cleancache",
+};
+
+#endif /* CONFIG_SYSFS */
+
+static int __init init_cleancache(void)
+{
+#ifdef CONFIG_SYSFS
+ int err;
+
+ err = sysfs_create_group(mm_kobj, &cleancache_attr_group);
+#endif /* CONFIG_SYSFS */
+ return 0;
+}
+module_init(init_cleancache)